Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

2015/10/21 by Wang, Peilu, Qian, Yao, Soong, Frank K. +2
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1510.06168

Abstract

Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e.g. speech utterances or handwritten documents. While word embedding has been demoed as a powerful representation for characterizing the statistical properties of natural language. In this study, we propose to use BLSTM-RNN with word embedding for part-of-speech (POS) tagging task. When tested on Penn Treebank WSJ test set, a state-of-the-art performance of 97.40 tagging accuracy is achieved. Without using morphological features, this approach can also achieve a good performance comparable with the Stanford POS tagger.

Related

• A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding
• Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss
• External Lexical Information for Multilingual Part-of-Speech Tagging
• Towards JointUD: Part-of-speech Tagging and Lemmatization using Recurrent Neural Networks
• Part-of-Speech Tagging with Minimal Lexicalization